• Corpus ID: 250311928

Critical Window of The Symmetric Perceptron

@inproceedings{Altschuler2022CriticalWO,
  title={Critical Window of The Symmetric Perceptron},
  author={Dylan J. Altschuler},
  year={2022}
}
We study the critical window of the symmetric binary perceptron, or equivalently, combinatorial discrepancy. Consider the problem of finding a binary vector σ satisfying ‖Aσ‖∞ ≤ K, where A is an αn×n matrix with iid Gaussian entries. For fixed K, at which densities α is this constraint satisfaction problem (CSP) satisfiable? A sharp threshold was recently established by Perkins and Xu [28], and Abbe, Li, and Sly [2], answering this to first order. Namely, for each K there exists an explicit… 
[PDF] Semantic Reader

References

SHOWING 1-10 OF 38 REFERENCES

Capacity lower bound for the Ising perceptron

This paper shows that the Krauth–Mézard conjecture α⋆ is a lower bound with positive probability, under the condition that an explicit univariate function S(λ) is maximized at λ=0.83.

Algorithms and Barriers in the Symmetric Binary Perceptron Model

It is shown that at high enough densities the SBP exhibits the multi Overlap Gap Property (m-OGP), an intricate geometrical property known to be a rigorous barrier for large classes of algorithms.

Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

We consider the symmetric binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory…

Frozen 1-RSB structure of the symmetric Ising perceptron

It is proved, under an assumption on the critical points of a real-valued function, that the symmetric Ising perceptron exhibits the `frozen 1-RSB' structure; that is, typical solutions of the model lie in clusters of vanishing entropy density.

Balancing Gaussian vectors in high dimension

A randomized polynomial-time algorithm is presented that achieves discrepancy $e^{-\Omega(\log^2(n)/m)}$ with high probability, provided that $m \leq O(\sqrt{\log{n}})$.

Storage capacity in symmetric binary perceptrons

The replica method is used to estimate the capacity threshold for the rectangle-binary-perceptron case when the u-function is wide and it is concluded that full-step-replica-symmetry breaking would have to be evaluated in order to obtain the exact capacity in this case.

Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster

It is shown that at low constraint density, there exists indeed a subdominant connected cluster of solutions with almost maximal diameter, and that an efficient multiscale majority algorithm can find solutions in such a cluster with high probability, settling in particular an open problem posed by Perkins-Xu in STOC'21.

Integer Feasibility of Random Polytopes

We study integer programming instances over polytopes P(A,b)={x:Ax<=b} where the constraint matrix A is random, i.e., its entries are i.i.d. Gaussian or, more generally, its rows are i.i.d. from a…

The Phase Transition of Discrepancy in Random Hypergraphs

This work applies the partial colouring lemma of Lovett and Meka to show that w.h.p. has discrepancy O( √ dn/m log(m/n), and characterizes how the discrepancy of each random hypergraph model transitions from â‚ d to o(√ d) as m varies from m = Θ(n) to m n.

Six standard deviations suffice

Given n sets on n elements it is shown that there exists a two-coloring such that all sets have discrepancy at most Knl/2, K an absolute constant. This improves the basic probabilistic method with…